Telefonica: Big Data, Machine Learning (ML) and Artificial Intelligence (AI) to Connect the Unconnected

Earlier, I wrote a detailed post on how Telefonica was on a mission to connect 100 Million Unconnected with their 'Internet para todos' initiative. This video below is a good advert of what Telefinica is trying to achieve in Latin America


I recently came across a LinkedIn post on how Telefónica uses AI / ML to connect the unconnected by Patrick Lopez, VP Networks Innovation @ Telefonica. It was no brainer that this needs to be shared.

Big data for social good from Patrick Lopez

In his post, Patrick mentions the following:

To deliver internet in these environments in a sustainable manner, it is necessary to increase efficiency through systematic cost reduction, investment optimization and targeted deployments.

Systematic optimization necessitates continuous measurement of the financial, operational, technological and organizational data sets.

1. Finding the unconnected

The first challenge the team had to tackle was to understand how many unconnected there are and where. The data set was scarce and incomplete, census was old and population had much mobility. In this case, the team used high definition satellite imagery at the scale of the country and used neural network models, coupled with census data as training. Implementing visual machine learning algorithms, the model literally counted each house and each settlement at the scale of the country. The model was then enriched with crossed reference coverage data from regulatory source, as well as Telefonica proprietary data set consisting of geolocalized data sessions and deployment maps. The result is a model with a visual representation, providing a map of the population dispersion, with superimposed coverage polygons, allowing to count and localize the unconnected populations with good accuracy (95% of the population with less than 3% false positive and less than 240 meters deviation in the location of antennas).


2. Optimizing transport

Transport networks are the most expensive part of deploying connectivity to remote areas. Optimizing transport route has a huge impact on the sustainability of a network. This is why the team selected this task as the next challenge to tackle.

The team started with adding road and infrastructure data to the model form public sources, and used graph generation to cluster population settlements. Graph analysis (shortest path, Steiner tree) yielded population density-optimized transport routes.


3. AI to optimize network operations

To connect very remote zones, optimizing operations and minimizing maintenance and upgrade is key to a sustainable operational model. This line of work is probably the most ambitious for the team. When it can take 3 hours by plane and 4 days by boat to reach some locations, being able to make sure you can detect, or better, predict if / when you need to perform maintenance on your infrastructure. Equally important is how your devise your routes so that you are as efficient as possible. In this case, the team built a neural network trained with historical failure analysis and fed with network metrics to provide a model capable of supervising the network health in an automated manner, with prediction of possible failure and optimized maintenance route.

I think that the type of data driven approach to complex problem solving demonstrated in this project is the key to network operators' sustainability in the future. It is not only a rural problem, it is necessary to increase efficiency and optimize deployment and operations to keep decreasing the costs.


Finally, its worth mentioning again that I am helping CW (Cambridge Wireless) organise their annual CW TEC conference on the topic 'The inevitable automation of Next Generation Networks'. There are some good speakers and we will have similar topics covered from different angles, using some other interesting approaches. The fees are very reasonable so please join if you can.

Related posts:

• Internet para todos: Telefonica and Parallel Wireless on a mission to connect 100 Million Unconnected
• Automating the 5G Core using Machine Learning and Data Analytics
• ITU 'Network 2030': Initiative to support Emerging Technologies and Innovation looking beyond 5G advances
• Artificial Intelligence - Beyond SON for Autonomous Networks
• Twitter et al. for Small Cell Planning

Changes in LTE pricing strategies

Its been a while since I blogged about pricing strategies (see old posts here, here and here). I recently enjoyed listening to Soichi Nakajima, Director of "Digital Telco and OTT" at IDATE DigiWorld when he presented a talk on LTE pricing strategy. The slides are embedded below

Supply-side strategies: from LTE to 5G - IDATE from techUK

I think the slides are self-explanatory but here is the summary worth highlighting:

How LTE plans have changed: shift in focus from data allowance to quality of service 

• Mobile data services are still largely structured by on data allowance, but high volume and unlimited plans are increasingly common. 
• Unlimited does not necessarily mean high-end: some target users with a small budget, providing a very slow connection. 
• Quality of service becoming central in structuring product lines – especially speed which my or may not be combined with data caps – as is content quality. 
• Certain applications being favoured through zero rating (traffic not deducted from the customer’s allowance). This can be a way to market unlimited plans and avoid fixed-mobile substitution. 
• Growing number of partnerships with OTT video services, rather than selling premium content plans, which are tending to wane.

The slides are available to download from techUK page here. There is also a bonus presentation on "How to address the challenges of providing connectivity on trains".

ITU 'Network 2030': Initiative to support Emerging Technologies and Innovation looking beyond 5G advances

Source: ITU

As per this recent ITU Press Release:

The International Telecommunication Union, the United Nations specialized agency for information and communication technology (ICT), has launched a new research initiative to identify emerging and future ICT sector network demands, beyond 2030 and the advances expected of IMT-2020 (5G) systems. This work will be carried out by the newly established ITU Focus Group on Technologies for Network 2030, which is open to all interested parties.

The ITU focus group aims to guide the global ICT community in developing a "Network 2030" vision for future ICTs. This will include new concepts, new architecture, new protocols – and new solutions – that are fully backward compatible, so as to support both existing and new applications.

"The work of the ITU Focus Group on Technologies for 'Network 2030' will provide network system experts around the globe with a very valuable international reference point from which to guide the innovation required to support ICT use cases through 2030 and beyond," said ITU Secretary-General Houlin Zhao.

These ICT use cases will span new media such as hologrammes, a new generation of augmented and virtual reality applications, and high-precision communications for 'tactile' and 'haptic' applications in need of processing a very high volume of data in near real-time – extremely high throughput and low latency.   

Emphasizing this need, the focus group's chairman, Huawei's Richard Li, said, "This Focus Group will look at new media, new services and new architectures. Holographic type communications will have a big part to play in industry, agriculture, education, entertainment – and in many other fields. Supporting such capabilities will call for very high throughput in the range of hundreds of gigabits per second or even higher."

The ITU Focus Group on Technologies for 'Network 2030' is co-chaired by Verizon's Mehmet Toy, Rostelecom's Alexey Borodin, China Telecom's Yuan Zhang, Yutaka Miyake from KDDI Research, and is coordinated through ITU's Telecommunication Standardization Sector – which works with ITU's 193 Member States and more than 800 industry and academic members to establish international standards for emerging ICT innovations.

The ITU focus group reports to and will inform a new phase of work of the ITU standardization expert group for 'Future Networks' – Study Group 13. It will also strengthen and leverage collaborative relationships with and among other standards development organizations including: The European Telecommunications Standards Institute (ETSI), the Association for Computing Machinery's Special Interest Group on Data Communications (ACM SIGCOMM), and the Institute of Electrical and Electronics Engineers' Communications Society (IEEE ComSoc).

Source: ITU

According to the Focus Group page:

The FG NET-2030, as a platform to study and advance international networking technologies, will investigate the future network architecture, requirements, use cases, and capabilities of the networks for the year 2030 and beyond. 

The objectives include: 

• To study, review and survey existing technologies, platforms, and standards for identifying the gaps and challenges towards Network 2030, which are not supported by the existing and near future networks like 5G/IMT-2020.
• To formulate all aspects of Network 2030, including vision, requirements, architecture, novel use cases, evaluation methodology, and so forth.
• To provide guidelines for standardization roadmap.
• To establish liaisons and relationships with other SDOs.

An ITU interview with Dr. Richard Li, Huawei, Chairman of the ITU-T FG on Network 2030 is available on YouTube here.

A recent presentation by Dr. Richard Li on this topic is embedded below:

Towards a New Internet for the Year 2030 and Beyond from 3G4G

First Workshop on Network 2030 will be held in New York City, United States on 2 October 2018. Details here.

Related News:

• ITU News: ITU launches new study on networks & technologies for 2030 and beyond